BackgroundAccurate histological grading of oral squamous cell carcinoma (OSCC) is critical for prognosis and treatment planning. Current methods lack automation for OSCC detection, subtyping, and differentiation from high-risk pre-malignant conditions like oral submucous fibrosis (OSMF). Further, analysis of whole-slide image (WSI) analysis is time-consuming and variable, limiting consistency. We present a clinically relevant deep learning framework that leverages weakly supervised learning and attention-based multiple instance learning (MIL) to enable automated OSCC grading and early prediction of malignant transformation from OSMF. MethodsWe conducted a multi-institutional retrospective cohort study using a curated dataset of 1,925 whole-slide images (WSIs), including 1,586 OSCC cases stratified into well-, moderately-, and poorly-differentiated subtypes (WD, MD, and PD), 128 normal controls, and 211 OSMF and OSMF with OSCC cases. We developed a two-stage deep learning pipeline named OralPatho. In stage one, an attention-based multiple instance learning (MIL) model was trained to perform binary classification (normal vs OSCC). In stage two, a gated attention mechanism with top-K patch selection was employed to classify the OSCC subtypes. Model performance was assessed using stratified 3-fold cross-validation and external validation on an independent dataset. FindingsThe binary classifier demonstrated robust performance with a mean F1-score exceeding 0.93 across all validation folds. The multiclass model achieved consistent macro-F1 scores of 0.72, 0.70, and 0.68, along with AUCs of 0.79 for WD, 0.71 for MD, and 0.61 for PD OSCC subtypes. Model generalizability was validated using an independent external dataset. Attention maps reliably highlighted clinically relevant histological features, supporting the systems interpretability and diagnostic alignment with expert pathological assessment. InterpretationThis study demonstrates the feasibility of attention-based, weakly supervised learning for accurate OSCC grading from whole-slide images. OralPatho combines high diagnostic performance with real-time interpretability, making it a scalable solution for both advanced pathology labs and resource-limited settings.

Ocular and non-ocular diseases significantly impact millions of people worldwide, leading to vision impairment or blindness if not detected and managed early. Many individuals could be prevented from becoming blind by treating these diseases early on and stopping their progression. Despite advances in medical imaging and diagnostic tools, the manual detection of these diseases remains labor-intensive, time-consuming, and dependent on the expert's experience. Computer-aided diagnosis (CAD) has been transformed by machine learning (ML), providing promising methods for the automated detection and grading of diseases using various retinal imaging modalities. In this paper, we present a comprehensive systematic literature review that discusses the use of ML techniques to detect diseases from retinal images, utilizing both single and multi-modal imaging approaches. We analyze the efficiency of various Deep Learning and classical ML models, highlighting their achievements in accuracy, sensitivity, and specificity. Even with these advancements, the review identifies several critical challenges. We propose future research directions to address these issues. By overcoming these challenges, the potential of ML to enhance diagnostic accuracy and patient outcomes can be fully realized, opening the way for more reliable and effective ocular and non-ocular disease management.

The aim of this study was to automatically detect teeth with dens invaginatus (DI) in panoramic radiographs using deep learning algorithms and to compare the success of the algorithms. For this purpose, 400 panoramic radiographs with DI were collected from the faculty database and separated into 60% training, 20% validation and 20% test images. The training and validation images were labeled by oral, dental and maxillofacial radiologists and augmented with various augmentation methods, and the improved models were asked for the images allocated for the test phase and the results were evaluated according to performance measures including accuracy, sensitivity, F1 score and mean detection time. According to the test results, YOLOv8 achieved a precision, sensitivity and F1 score of 0.904 and was the fastest detection model with an average detection time of 0.041. The Faster R-CNN model achieved 0.912 precision, 0.904 sensitivity and 0.907 F1 score, with an average detection time of 0.1 s. The YOLOv9 algorithm showed the most successful performance with 0.946 precision, 0.930 sensitivity, 0.937 F1 score value and the average detection speed per image was 0.158 s. According to the results obtained, all models achieved over 90% success. YOLOv8 was relatively more successful in detection speed and YOLOv9 in other performance criteria. Faster R-CNN ranked second in all criteria.

Osteoporosis is a prevalent skeletal disorder characterized by reduced bone mineral density (BMD) and structural deterioration, resulting in increased fracture risk. Early diagnosis is crucial to prevent fractures and improve patient outcomes. This study investigates the diagnostic utility of morphometric and cortical indices derived from cone-beam computed tomography (CBCT) for identifying osteoporotic postmenopausal women who were candidates for dental implant therapy, with dual-energy X-ray absorptiometry (DXA) used as the reference standard. This cross-sectional study included 71 postmenopausal women, aged 50-79 years, who underwent CBCT imaging at the Oral and Maxillofacial Radiology Department of Hamadan University of Medical Sciences between 2022 and 2024. Participants with systemic conditions affecting bone metabolism were excluded. The morphometric indices-Computed Tomography Mandibular Index (CTMI), Computed Tomography Index Superior (CTI(S)), Computed Tomography Index Inferior (CTI(I)), and Computed Tomography Cortical Index (CTCI)-were measured at the mental foramen and antegonial regions using OnDemand3D Dental software. Bone mineral density (BMD) was assessed by DXA scans of the lumbar spine and femoral neck. In addition to traditional statistical analyses (Pearson's correlation and one-way ANOVA with LSD test), a multilayer perceptron (MLP) neural network model was employed to evaluate the diagnostic power of CBCT indices. DXA results based on the femoral neck T-scores categorized 38 patients as normal, 32 as osteopenic, and one as osteoporotic, while lumbar spine T-scores identified 38 normal, 22 osteopenic, and 11 osteoporotic patients. Significant differences (p < 0.05) were observed in most CBCT-derived indices, with the CTMI index demonstrating the most marked variation, especially between normal and osteoporotic groups (p < 0.001). Moreover, significant positive correlations were found between the CBCT indices and DXA T-scores across the lumbar spine, femoral neck, and total hip regions. The neural network model achieved an overall diagnostic accuracy of 75%, with the highest predictive importance attributed to antegonial CTCI and CTMI indices. This study highlights the significant correlation between CBCT-derived radiomorphometric indices such as CTMI, CTI(S), CTI(I), and CTCI at the mental foramen and antegonial regions and bone mineral density (BMD) in postmenopausal women. CBCT, particularly the CTMI index in the antegonial region, offers a cost-effective, non-invasive method for early osteoporosis detection, providing a valuable alternative to traditional screening methods.

Transparency is a paramount concern in the medical field, prompting researchers to delve into the realm of explainable AI (XAI). Among these XAI methods, Concept Bottleneck Models (CBMs) aim to restrict the model's latent space to human-understandable high-level concepts by generating a conceptual layer for extracting conceptual features, which has drawn much attention recently. However, existing methods rely solely on concept features to determine the model's predictions, which overlook the intrinsic feature embeddings within medical images. To address this utility gap between the original models and concept-based models, we propose Vision Concept Transformer (VCT). Furthermore, despite their benefits, CBMs have been found to negatively impact model performance and fail to provide stable explanations when faced with input perturbations, which limits their application in the medical field. To address this faithfulness issue, this paper further proposes the Stable Vision Concept Transformer (SVCT) based on VCT, which leverages the vision transformer (ViT) as its backbone and incorporates a conceptual layer. SVCT employs conceptual features to enhance decision-making capabilities by fusing them with image features and ensures model faithfulness through the integration of Denoised Diffusion Smoothing. Comprehensive experiments on four medical datasets demonstrate that our VCT and SVCT maintain accuracy while remaining interpretable compared to baselines. Furthermore, even when subjected to perturbations, our SVCT model consistently provides faithful explanations, thus meeting the needs of the medical field.

Temporomandibular disorders (TMDs) are frequently associated with posterior condylar displacement; however, early prediction of this displacement remains a significant challenge. Therefore, in this study, we aimed to develop and evaluate a predictive model for bilateral posterior condylar displacement. In this retrospective observational study, 166 cone-beam computed tomography images were examined and categorized into two groups based on condyle positions as observed in the sagittal images of the joint space: those with bilateral posterior condylar displacement and those without. Three machine-learning algorithms-Random Forest, Least Absolute Shrinkage and Selection Operator (LASSO) regression, and Extreme Gradient Boosting (XGBoost)-were used to identify risk factors and establish a risk assessment model. Calibration curves, receiver operating characteristic curves, and decision curve analyses were employed to evaluate the accuracy of the predictions, differentiation, and clinical usefulness of the models, respectively. Articular eminence inclination (AEI) and age were identified as significant risk factors for bilateral posterior condylar displacement. The area under the curve values for the LASSO and Random Forest models were both > 0.7, indicating satisfactory discriminative ability of the nomogram. No significant differences were observed in the differentiation and calibration performance of the three models. Clinical utility analysis revealed that the LASSO regression model, which incorporated age, AEI, A point-nasion-B point (ANB) angle, and facial height ratio (S-Go/N-Me), demonstrated superior net benefit compared to the other models when the probability threshold exceeded 45%. Patients with a steeper AEI, insufficient posterior vertical distance (S-Go/N-Me), an ANB angle ≥ 4.7°, and older age are more likely to experience bilateral posterior condylar displacement. The prognostic nomogram developed and validated in this study may assist clinicians in assessing the risk of bilateral posterior condylar displacement.

To assess the suitability of Transformer-based architectures for medical image segmentation and investigate the potential advantages of Graph Neural Networks (GNNs) in this domain. We analyze the limitations of the Transformer, which models medical images as sequences of image patches, limiting its flexibility in capturing complex and irregular tumor structures. To address it, we propose U-GNN, a pure GNN-based U-shaped architecture designed for medical image segmentation. U-GNN retains the U-Net-inspired inductive bias while leveraging GNNs' topological modeling capabilities. The architecture consists of Vision GNN blocks stacked into a U-shaped structure. Additionally, we introduce the concept of multi-order similarity and propose a zero-computation-cost approach to incorporate higher-order similarity in graph construction. Each Vision GNN block segments the image into patch nodes, constructs multi-order similarity graphs, and aggregates node features via multi-order node information aggregation. Experimental evaluations on multi-organ and cardiac segmentation datasets demonstrate that U-GNN significantly outperforms existing CNN- and Transformer-based models. U-GNN achieves a 6% improvement in Dice Similarity Coefficient (DSC) and an 18% reduction in Hausdorff Distance (HD) compared to state-of-the-art methods. The source code will be released upon paper acceptance.

Self-supervised methods for magnetic resonance imaging (MRI) reconstruction have garnered significant interest due to their ability to address the challenges of slow data acquisition and scarcity of fully sampled labels. Current regularization-based self-supervised techniques merge the theoretical foundations of regularization with the representational strengths of deep learning and enable effective reconstruction under higher acceleration rates, yet often fall short in interpretability, leaving their theoretical underpinnings lacking. In this paper, we introduce a novel self-supervised approach that provides stringent theoretical guarantees and interpretable networks while circumventing the need for fully sampled labels. Our method exploits the intrinsic relationship between convolutional neural networks and the null space within structural low-rank models, effectively integrating network parameters into an iterative reconstruction process. Our network learns gradient descent steps of the projected gradient descent algorithm without changing its convergence property, which implements a fully interpretable unfolded model. We design a non-expansive mapping for the network architecture, ensuring convergence to a fixed point. This well-defined framework enables complete reconstruction of missing <math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mi>k</mi> <annotation>$k$</annotation></semantics> </math> -space data grounded in matrix completion theory, independent of fully sampled labels. Qualitative and quantitative experimental results on multi-coil MRI reconstruction demonstrate the efficacy of our self-supervised approach, showing marked improvements over existing self-supervised and traditional regularization methods, achieving results comparable to supervised learning in selected scenarios. Our method surpasses existing self-supervised approaches in reconstruction quality and also delivers competitive performance under supervised settings. This work not only advances the state-of-the-art in MRI reconstruction but also enhances interpretability in deep learning applications for medical imaging.

Universal medical image segmentation using the Segment Anything Model (SAM) remains challenging due to its limited adaptability to medical domains. Existing adaptations, such as MedSAM, enhance SAM's performance in medical imaging but at the cost of reduced generalization to unseen data. Therefore, in this paper, we propose SAM-aware Test-Time Adaptation (SAM-TTA), a fundamentally different pipeline that preserves the generalization of SAM while improving its segmentation performance in medical imaging via a test-time framework. SAM-TTA tackles two key challenges: (1) input-level discrepancies caused by differences in image acquisition between natural and medical images and (2) semantic-level discrepancies due to fundamental differences in object definition between natural and medical domains (e.g., clear boundaries vs. ambiguous structures). Specifically, our SAM-TTA framework comprises (1) Self-adaptive Bezier Curve-based Transformation (SBCT), which adaptively converts single-channel medical images into three-channel SAM-compatible inputs while maintaining structural integrity, to mitigate the input gap between medical and natural images, and (2) Dual-scale Uncertainty-driven Mean Teacher adaptation (DUMT), which employs consistency learning to align SAM's internal representations to medical semantics, enabling efficient adaptation without auxiliary supervision or expensive retraining. Extensive experiments on five public datasets demonstrate that our SAM-TTA outperforms existing TTA approaches and even surpasses fully fine-tuned models such as MedSAM in certain scenarios, establishing a new paradigm for universal medical image segmentation. Code can be found at https://github.com/JianghaoWu/SAM-TTA.

Deep learning models have shown remarkable success in dermatological image analysis, offering potential for automated skin disease diagnosis. Previously, convolutional neural network(CNN) based architectures have achieved immense popularity and success in computer vision (CV) based task like skin image recognition, generation and video analysis. But with the emergence of transformer based models, CV tasks are now are nowadays carrying out using these models. Vision Transformers (ViTs) is such a transformer-based models that have shown success in computer vision. It uses self-attention mechanisms to achieve state-of-the-art performance across various tasks. However, their reliance on global attention mechanisms makes them susceptible to adversarial perturbations. This paper aims to investigate the susceptibility of ViTs for medical images to adversarial watermarking-a method that adds so-called imperceptible perturbations in order to fool models. By generating adversarial watermarks through Projected Gradient Descent (PGD), we examine the transferability of such attacks to CNNs and analyze the performance defense mechanism -- adversarial training. Results indicate that while performance is not compromised for clean images, ViTs certainly become much more vulnerable to adversarial attacks: an accuracy drop of as low as 27.6%. Nevertheless, adversarial training raises it up to 90.0%.